报告题目:Pretrained Transform-Based Tensor Representations
报告人:电子科技大学 赵熙乐教授
报告时间:2026年8月10日 9:00-10:00
报告地点:动漫a片
106会议室
报告摘要:Recently, Fourier transform-based tensor representations have been suggested for processing and analyzing multi-dimensional data arising from real-world applications, where transform and the corresponding latent tensor serve as the two building blocks of this framework. From both perspectives, this talk will review recent progress in transform-based tensor representations. On one hand, we will discuss the evolution of the transform from linear and shallow ones to nonlinear and deep ones. On the other hand, we will discuss the evolution of the corresponding latent tensor from shallow and untrained ones to deep and pretrained ones. Finally, we will also discuss the limitations and future possibilities of the transform-based tensor representation.
报告人简介:担任中国工业与应用数学学会副秘书长和青年工作委员会秘书长,入选国家高层次青年人才、“全球前2%顶尖科学家榜单”年度科学影响力排行榜、四川省学术和技术带头人、四川省青年人才、电子科技大学百人计划。科研方面,主要研究兴趣为数学和人工智能交叉研究,撰写Elsevier出版社和科学出版社出版的学术专著章节2章,第一/通讯在在数学和信息领域知名期刊和会议发表学术论文100余篇(Google学术引用8000余次),包括权威期刊SIAM J. Sci. Comput.、SIAM J. Imaging Sci.、IEEE Trans. Pattern Anal. Mach. Intell.、IEEE Trans. Signal Process.、IEEE Trans. Image Process.、IEEE Trans. Comput. Imaging、IEEE Trans. Intell. Transp. Syst.、IEEE Trans. Neural Netw. Learn. Syst.、IEEE Trans. Cybernetics、IEEE Trans. Circuits Syst. Video Technol .、IEEE Trans. Geosci. Remote Sens.和IEEE Trans. Big Data及顶会CVPR、ECCV、AAAI和ACM MM等。主持国家自然科学基金3项、四川省杰出青年科学基金项目、华为项目2项等。研究成果获四川省自然科学一等奖、四川省科技进步一等奖、中国计算数学学会青年优秀论文竞赛二等奖、第一、第二届连续两届川渝科技学术大会优秀论文一等奖(每届全省仅十名)、首届四川省数学会应用数学奖二等奖(独立完成)。担任Computational Intelligence、Optik和Remote Sensing客座编委、《西南交通大学学报》青年编委。